Reinforcement Schedules
Multi-input and Multi-variable systems
Cooperative Allosteric Transitions
Multi-Step Reactions
Associative Learning
Sampling Plans
您也可能阅读
通过共同作者、期刊和引用图与本文相关的文章。
Mingxiao Feng1, Yaodong Yang2, Wengang Zhou1
1CAS Key Laboratory of GIPAS, University of Science and Technology of China, Hefei, China; Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China.
在多代理强化学习 (MARL) 中提高数据效率至关重要. 新的过渡信息化多代理代表 (TIMAR) 框架使用世界模型来提高代理协调和学习效率.
科学领域:
背景情况:
研究的目的:
主要方法:
主要成果:
结论: